Neuro-symbolic artificial intelligence

Issue title: Historical and Future Perspectives of AI

Subtitle: Current trends

Article type: Research Article

Authors: Sarker, Md Kamruzzaman^a | Zhou, Lu^b | Eberhart, Aaron^b | Hitzler, Pascal^{b; *}

Affiliations: [a] Department of Computing Sciences, University of Hartford, CT, USA | [b] Department of Computer Science, Kansas State University, KS, USA

Correspondence: [*] Corresponding author. E-mail: [email protected].

Abstract: Neuro-Symbolic Artificial Intelligence – the combination of symbolic methods with methods that are based on artificial neural networks – has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is meant to serve as a convenient starting point for research on the general topic.

Keywords: Artificial neural networks, deep learning, knowledge representation and reasoning, neuro-symbolic artificial intelligence

DOI: 10.3233/AIC-210084

Journal: AI Communications, vol. 34, no. 3, pp. 197-209, 2021